All Open Source Apps

An incremental data indexing engine that keeps AI agent context perpetually fresh by reprocessing only what changed.

A temporal, verifiable graph database with git-like branching, integrated vector/text/geo search, and RDF/SPARQL/JSON-LD/openCypher support — benchmarked at 10.4x faster than the next database on the full Wikidata dump.

Free, offline, open-source speech-to-text that pastes directly into any app on Windows, macOS, and Linux.

Compose, extend, and observe every backend service in real time using three primitives: Workers, Functions, and Triggers.

Privacy-first AI meeting assistant that transcribes and summarizes your meetings entirely on your local machine — no cloud, no data leakage.

Run LLM-generated Python code safely inside your agent—no containers, no CPython, no compromise—with sub-microsecond startup.

Stateful actors as a primitive for AI agents, real-time collaboration, and durable execution — with in-memory state, WebSockets, queues, and scheduling built in.

A graph-vector database built from scratch in Rust that unifies graph traversal, vector search, key-value, and relational storage into a single platform for AI applications.

Self-hosted secure remote access that unifies WireGuard VPN, identity management, and connection-level MFA in one open-source platform.

The safe, private runtime that lets autonomous AI agents operate in sandboxed environments governed by declarative YAML policies — blocking data exfiltration, credential leaks, and unauthorized network activity before they happen.

A production-ready 2D/3D game engine written in Rust with a built-in scene editor, physics, and hot-reloading game scripts

A free, open source procedural 2D design tool that unifies vector, raster, motion graphics, and generative art in a single node-based nondestructive workflow.

Mesh LLM pools GPUs and memory across every machine you own into one OpenAI-compatible API, so agents tap distributed compute instead of a single GPU box or a metered cloud bill.

A terminal-native agent multiplexer that runs Claude, Codex, Gemini, and other coding agents side by side in real, persistent panes you can detach from and reattach to from anywhere.

Open-source Webhooks-as-a-Service: deliver events to your users with auto-retry, signed payloads, and a real-time subscriber dashboard — all without building the infrastructure yourself.

Open-source time-series database built for real-time ingest, fast SQL queries, and embedded Python automation — powered by Apache Arrow and Parquet.

A fast, lightweight, open-source document parser that extracts spatial text, bounding boxes, and Markdown from PDFs and Office files — entirely on your machine.

AI-powered file type detection that identifies 200+ content types with ~99% accuracy in milliseconds using a compact deep learning model.

A lightweight, stealthy headless browser written in Rust — drop-in compatible with Puppeteer and Playwright, built for AI agents and web scraping at scale.

Define AI agent workflows as code graphs, route tasks across any LLM, and intervene only where it matters.

Like htop, but for your AI coding agents — monitor Claude Code, Codex CLI, and OpenCode sessions, tokens, context windows, rate limits, and orphan ports all from one terminal screen.

An open-source, AI-native vector design tool with concurrent agent teams, design-as-code, a built-in MCP server, and multi-model intelligence — a distinct project from the similarly-named Figma-file-reading "open-pencil" editor.

Lightweight, S3-compatible object storage built for geo-distributed self-hosting across unreliable internet connections.

Self-hosted, end-to-end encrypted cloud storage with browser-based encryption and S3-compatible storage support